© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129656
    Prev
    Next
    INDEX
    Explanations

    date, name, chemical, number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     både
    -0.07
    Both
    -0.07
     both
    -0.06
     zowel
    -0.06
    both
    -0.06
     Both
    -0.06
     সন্ত্রাসী
    -0.06
    press
    -0.05
     kinda
    -0.05
     völlig
    -0.05
    POSITIVE LOGITS
     fakat
    0.06
     부산
    0.06
     bege
    0.06
     достой
    0.06
     surfer
    0.06
     znamen
    0.06
     অধিনায়ক
    0.06
    request
    0.06
     باقی
    0.06
     નામ
    0.06
    Activations Density 0.001%

    No Known Activations